Uncensored LLM API

OpenRouter dolphin ai Uncensored API

Get direct access to the uncensored Dolphin model with a 100k token context window, bypassing router rate limits for reliable NSFW and roleplay generation.

100k context window support
Pay $0.15 per 1M input tokens
No content training on prompts

Create key View documentation

Test with one API call

curl https://api.openrouterdolphinai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Fix the syntax error in this python function"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.openrouterdolphinai.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openrouterdolphinai.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

per 1M input tokens: $0.15
Output tokens / 1M: $0.50
token context: 100,000
trial credit: $0.50
requests per minute: 300

Core features

Direct Model Access

Run the uncensored Dolphin model on dedicated servers without multi-model routing variability.

OpenAI Compatible

Drop-in replacement using standard endpoints and the official OpenAI SDK for your client.

High Capacity

Handle long context windows up to 100,000 tokens with 16,000 token max output.

Transparent Pricing

Pay only for real token usage with prepaid credit that never expires or fees.

Crypto Top-ups

Fund your account easily with USDT or USDC and receive bonus credit on deposits.

Streaming Support

Receive real-time token data via Server-Sent Events with usage stats in the final chunk.

Setup guide

Create Account

Top Up Credit

Add crypto funds starting at $20 to unlock the API with potential bonus credits.

Send Request

Point your client to our base URL and start generating text with the uncensored model.

Common use cases

Unrestricted Roleplay

Generate diverse character dialogues without content filters blocking mature or controversial fictional themes.

NSFW Content Generation

Create adult-oriented text stories and scenes with high reliability and no sudden refusals.

Developer Testing

Integrate an open-weight model into your application for consistent uncensored response handling.

Long Context Analysis

Process large documents using the 100k token window for comprehensive text understanding tasks.

openrouter dolphin AI: The Uncensored API Alternative

Stop routing traffic through multi-model gateways and get direct access to a dedicated uncensored LLM.

Reliable NSFW Generation

Eliminate random refusals from shared routers. Our isolated server runs the model without third-party filters, ensuring consistent output for adult content and creative writing.

Predictable Latency

No more variability from other users sharing the same endpoint. Dedicated hardware delivers stable performance for roleplay bots that require low-latency streaming.

Transparent Crypto Pricing

Pay exactly for tokens used. Top up with USDT or USDC, start with $0.50 trial credit, and never pay for errors or unused capacity.

How to Spot a True Uncensored API (vs. Routers)

A true uncensored API isolates a single model on dedicated servers, ensuring high availability and predictable latency without the variability of multi-model routing. Routers often introduce hidden variability, rate limits, or unexpected refusals when traffic spikes. Our service delivers direct access to one powerful model with transparent pricing.

Feature	Typical Router	Our API
Model Access	Multiple models routed	Single dedicated model
Predictability	Variable latency	Consistent performance
Content Filtering	Often applied by router	Direct model output

What Developers Ask: Rate Limits, Context & Errors

Our API enforces strict limits to ensure stability: 300 requests per minute, 8 concurrent connections, and an 8 MB request body. You receive a 100,000 token context window, with a default 2,048 token output cap unless you specify max_tokens. Unlike free tiers that randomly throttle usage, we guarantee predictable latency for paid credits. Errors incur no charge, and our single-model architecture avoids the routing delays common in multi-vendor routers.

Start generating responses immediately with this straightforward workflow.

Sign up: Use Google or email to create an account; no phone number is required.
Get your key: Retrieve your unique API key instantly from the dashboard.
Add credit: Top up with USDT or USDC to activate your service.
Send requests: Point your OpenAI-compatible SDK to our base URL and begin streaming results.

Migrate Your OpenAI Code in 3 Lines

Switch to our uncensored API by updating three client parameters. Change the base URL to HTTPS://api.openrouterdolphinai.com/v1, set the model ID to "uncensored", and inject your new API key. The endpoint remains POST /v1/chat/completions, ensuring your existing logic works without modification. This direct approach eliminates router variability and ensures predictable latency for unrestricted text generation. base_url is the only required adjustment.

Common Mistakes in Uncensored LLM APIs

Developers often confuse model routing with model isolation. Routers introduce latency variance and unpredictable refusals when aggregating multiple endpoints. A true uncensored API serves a single, dedicated model on its own servers, ensuring stable 100,000-token context windows. Avoid providers claiming unlimited throughput; we enforce 300 requests per minute to guarantee reliability. Always verify the base URL matches your SDK configuration to prevent silent connection failures.

Frequently asked questions

What is openrouter dolphin AI and how does it differ from standard routers?

It is an uncensored API serving a single dedicated model without multi-model routing. You get direct access to the uncensored LLM on our servers. This ensures predictable latency and avoids the variability of aggregators that switch between vendors.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

Does this uncensored AI service store my prompts for training?

No, we do not use your data for training. Your privacy is protected because prompts are not used to improve the model. An account requires only an email address, ensuring minimal data collection while you generate unrestricted content.

What is the maximum context window for a single request?

The model supports a 100,000 token context window combining both prompt and completion. You can generate up to 16,000 tokens per request. If you do not set max_tokens, the default output limit is 2,048 tokens.

How do I add credit to my uncensored LLM account?

We accept only USDT on TRC20 or USDC on Base for top-ups. Payments range from $20 to $500 per transaction. You receive bonus credit of 5% from $50, 10% from $100, and 15% from $200.

Can I use standard OpenAI SDKs with this API?

Yes, the API is fully OpenAI compatible. You simply update the base_url and API key in your client code. It supports streaming, function calling, JSON mode, and standard parameters like temperature and top_p for reliable integration.

Get your API key

Create key